[<prev] [next>] [<thread-prev] [day] [month] [year] [list]
Date: Thu, 08 Aug 2019 15:55:27 -0700 (PDT)
From: David Miller <davem@...emloft.net>
To: gnault@...hat.com
Cc: netdev@...r.kernel.org, fw@...len.de, edumazet@...gle.com,
posk@...gle.com, alex.aring@...il.com
Subject: Re: [PATCH net] inet: frags: re-introduce skb coalescing for local
delivery
From: Guillaume Nault <gnault@...hat.com>
Date: Fri, 2 Aug 2019 17:15:03 +0200
> Before commit d4289fcc9b16 ("net: IP6 defrag: use rbtrees for IPv6
> defrag"), a netperf UDP_STREAM test[0] using big IPv6 datagrams (thus
> generating many fragments) and running over an IPsec tunnel, reported
> more than 6Gbps throughput. After that patch, the same test gets only
> 9Mbps when receiving on a be2net nic (driver can make a big difference
> here, for example, ixgbe doesn't seem to be affected).
>
> By reusing the IPv4 defragmentation code, IPv6 lost fragment coalescing
> (IPv4 fragment coalescing was dropped by commit 14fe22e33462 ("Revert
> "ipv4: use skb coalescing in defragmentation"")).
>
> Without fragment coalescing, be2net runs out of Rx ring entries and
> starts to drop frames (ethtool reports rx_drops_no_frags errors). Since
> the netperf traffic is only composed of UDP fragments, any lost packet
> prevents reassembly of the full datagram. Therefore, fragments which
> have no possibility to ever get reassembled pile up in the reassembly
> queue, until the memory accounting exeeds the threshold. At that point
> no fragment is accepted anymore, which effectively discards all
> netperf traffic.
>
> When reassembly timeout expires, some stale fragments are removed from
> the reassembly queue, so a few packets can be received, reassembled
> and delivered to the netperf receiver. But the nic still drops frames
> and soon the reassembly queue gets filled again with stale fragments.
> These long time frames where no datagram can be received explain why
> the performance drop is so significant.
>
> Re-introducing fragment coalescing is enough to get the initial
> performances again (6.6Gbps with be2net): driver doesn't drop frames
> anymore (no more rx_drops_no_frags errors) and the reassembly engine
> works at full speed.
>
> This patch is quite conservative and only coalesces skbs for local
> IPv4 and IPv6 delivery (in order to avoid changing skb geometry when
> forwarding). Coalescing could be extended in the future if need be, as
> more scenarios would probably benefit from it.
...
> Signed-off-by: Guillaume Nault <gnault@...hat.com>
Applied, thanks.
Powered by blists - more mailing lists